Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1953 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5502. Min Range: -5.5502
Max Act: 5.5502. Min Act: -0.1700
Data Index: 654815 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5502. Min Range: -5.5502
Max Act: 5.3940. Min Act: -0.1700
Data Index: 3338748 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5502. Min Range: -5.5502
Max Act: 5.3315. Min Act: -0.1700
Data Index: 654849 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5502. Min Range: -5.5502
Max Act: 5.3315. Min Act: -0.1700
Data Index: 8086480 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5502. Min Range: -5.5502
Max Act: 5.3315. Min Act: -0.1700
Data Index: 4588201 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5502. Min Range: -5.5502
Max Act: 5.3002. Min Act: -0.1700
Data Index: 3715899 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5502. Min Range: -5.5502
Max Act: 5.2377. Min Act: -0.1700
Data Index: 768897 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5502. Min Range: -5.5502
Max Act: 5.2377. Min Act: -0.1700
Data Index: 5207120 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5502. Min Range: -5.5502
Max Act: 5.2377. Min Act: -0.1700
Data Index: 3612461 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5502. Min Range: -5.5502
Max Act: 5.1752. Min Act: -0.1700
Data Index: 442172 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5502. Min Range: -5.5502
Max Act: 5.1752. Min Act: -0.1700
Data Index: 7297561 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5502. Min Range: -5.5502
Max Act: 5.1440. Min Act: -0.1700
Data Index: 1742808 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5502. Min Range: -5.5502
Max Act: 5.1440. Min Act: -0.1699
Data Index: 1175643 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5502. Min Range: -5.5502
Max Act: 5.1440. Min Act: -0.1700
Data Index: 7132330 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5502. Min Range: -5.5502
Max Act: 5.1127. Min Act: -0.1700
Data Index: 926185 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5502. Min Range: -5.5502
Max Act: 5.1127. Min Act: -0.1700
Data Index: 7297558 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5502. Min Range: -5.5502
Max Act: 5.1127. Min Act: -0.1700
Data Index: 1961695 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5502. Min Range: -5.5502
Max Act: 5.1127. Min Act: -0.1700
Data Index: 1002673 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5502. Min Range: -5.5502
Max Act: 5.0815. Min Act: -0.1700
Data Index: 5219000 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5502. Min Range: -5.5502
Max Act: 5.0815. Min Act: -0.1700
Data Index: 1002672 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19